R: The Swiss Army Knife of Science

• The R project for statistical computing is a free open source statistical programming language and project. Follow these steps to get started.
• The main advantages of R are the fact that R is freeware and that there is a lot of help available online.

Why use R?

• Strengths
  • free and open source, supported by a strong user community
  • highly extensible and flexible
  • implementation of modern statistical methods
  • assists with replication and extension of your work
• Weaknesses
  • slow with very large data sets (>1GB)
  • non-standard programming paradigms

Why use R?

• RStudio is the primary Integrated Develop Environment (IDE) for R
• We will be using RStudio for the tutorial

RStudio IDE

#

Packages/Libraries

• Packages are the main R tools
• There are 15388 packages. It’s probable that if you have thought about the analysis, there is a package that is able to do it already. There are two basic steps to using a package:

Installing the package install.packages("tidyverse")

Loading the package library(tidyverse)

Packages/Libraries

• Packages include functions that do things.

data <- read_csv(“/The/Path/To/Your/File.csv”)

• data = where you want to save the data
• <- = tell the function where to put the output
• read_csv = the name of the function
• () = what you input into the function

Doing simple things in R

## [1] 4

## [1] 8

Reading in some data

## Warning: Missing column names filled in: 'X21' [21], 'X22' [22],
## 'X23' [23], 'X24' [24], 'X25' [25], 'X26' [26]

## Parsed with column specification:
## cols(
##   .default = col_character(),
##   Region = col_double(),
##   Population = col_number(),
##   Census = col_double(),
##   `Election Year` = col_double(),
##   Sex = col_double(),
##   `ID Number` = col_logical(),
##   `Size of Council` = col_double(),
##   `Campaign Spending` = col_logical(),
##   X21 = col_logical(),
##   X22 = col_logical(),
##   X23 = col_logical(),
##   X24 = col_logical(),
##   X25 = col_logical(),
##   X26 = col_logical()
## )

## See spec(...) for full column specifications.

## Warning: 11 parsing failures.
##  row col expected actual                                                                            file
## 1185 Sex a double      . 'https://github.com/walkabillylab/lab_crossover_r/raw/master/nl_candidates.csv'
## 1628 Sex a double      . 'https://github.com/walkabillylab/lab_crossover_r/raw/master/nl_candidates.csv'
## 1807 Sex a double      . 'https://github.com/walkabillylab/lab_crossover_r/raw/master/nl_candidates.csv'
## 2878 Sex a double      . 'https://github.com/walkabillylab/lab_crossover_r/raw/master/nl_candidates.csv'
## 3222 Sex a double      . 'https://github.com/walkabillylab/lab_crossover_r/raw/master/nl_candidates.csv'
## .... ... ........ ...... ...............................................................................
## See problems(...) for more details.

Some quick descriptive statistics

## Warning: NAs introduced by coercion

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##     0.0     1.0    77.0   155.6   192.5  2034.0     548

Recoding a variable

## ── Attaching packages ────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.1     ✔ purrr   0.3.3
## ✔ tibble  2.1.3     ✔ dplyr   0.8.3
## ✔ tidyr   1.0.0     ✔ stringr 1.4.0
## ✔ ggplot2 3.2.1     ✔ forcats 0.4.0

## ── Conflicts ───────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

Recoding a variable

## Warning: Removed 548 rows containing non-finite values (stat_boxplot).

The great R wars

Two similar but different methods for many common tasks

• Tidyverse
• Base R

Where to find packages

• CRAN Task View
• META Cran
• Follow prominent voices
  • JennyBryan
  • Hadley Wickham
  • Amelia MN

Ocean Plastic Sciences

• marelac
• oce

Political Sciences

• http://m-clark.github.io/docs/RSocialScience.pdf
• Twitter Sentiment Analysis
  • https://dataaspirant.com/2018/03/22/twitter-sentiment-analysis-using-r/

Workflow Revolution

• RStudio + Github
  • https://github.com/TeamINTERACT/onboarding
• Full Scientific Paper with R and RMarkdown
  • Example1
  • Example2